Data as of

mcp-sequentialthinking-tools for VS Code: Setup & Config

VS Code: mcp-sequentialthinking-tools records stepwise reasoning with session history, branches, and revision metadata.

What you can do with mcp-sequentialthinking-tools in VS Code

Pick it for inspectable session-based planning with honest, limited tool-name validation.

  • Record explicit planning steps for a complex agent task
  • Validate proposed tool names against an explicitly supplied list

Before you start: mcp-sequentialthinking-tools in VS Code

  • npx
  • An MCP-compatible client

The history limit is per session and defaults to 1000. Its stdio transport accepts Content-Length framing and newline-delimited JSON used by older tmcp tooling.

mcp-sequentialthinking-tools VS Code configuration

  1. Choose VS Code configuration scope

    For mcp-sequentialthinking-tools, open Workspace: .vscode/mcp.json. Merge into servers; preserve existing inputs.

  2. Add mcp-sequentialthinking-tools to VS Code

    Use the mcp-sequentialthinking-tools entry below in servers. Keep mcp-sequentialthinking-tools's documented stdio connection fields and your other VS Code entries.

  3. Check mcp-sequentialthinking-tools in VS Code

    mcp-sequentialthinking-tools: Start in VS Code’s MCP controls; inspect output and trust prompts.

Config file · Workspace: .vscode/mcp.json

JSON
{
  "servers": {
    "mcp-sequentialthinking-tools": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mcp-sequentialthinking-tools"
      ],
      "env": {
        "MAX_HISTORY_SIZE": "<maximum recorded steps per session; default 1000>"
      }
    }
  }
}

mcp-sequentialthinking-tools tools available to VS Code

mcp-sequentialthinking-tools's stored tool list documents 3 tools; compare it with VS Code's connected tool list, because the stored list is not a live check.

sequentialthinking_tools

Look for sequentialthinking_tools among VS Code's agent-mode tools after starting mcp-sequentialthinking-tools through the MCP controls.

get_thinking_history

Look for get_thinking_history among VS Code's agent-mode tools after starting mcp-sequentialthinking-tools through the MCP controls.

Retrieve recorded session steps, optionally restricted by branch and record limit.

clear_thinking_history

Look for clear_thinking_history among VS Code's agent-mode tools after starting mcp-sequentialthinking-tools through the MCP controls.

Delete one session history or clear all session histories.

mcp-sequentialthinking-tools: full stored tool descriptions

Troubleshooting mcp-sequentialthinking-tools in VS Code

  • Make npx mcp-sequentialthinking-tools (Node.js/npm) available in the workspace, container, or remote environment hosting mcp-sequentialthinking-tools. Start through VS Code's MCP controls; inspect output and trust prompts.
  • For mcp-sequentialthinking-tools, keep MAX_HISTORY_SIZE out of version control; VS Code documents input variables and secret handling.
  • mcp-sequentialthinking-tools uses stdio here: VS Code must keep the configured process running; protocol output belongs on stdout and diagnostics on stderr.
  • Known limitation: Does not discover available tools or select tools for the model
  • Known limitation: Adds unnecessary overhead for trivial requests
  • Known limitation: Text filtering is not a guarantee against adversarial input
  • General VS Code troubleshooting lives in the /clients/vscode guide.

mcp-sequentialthinking-tools — details. VS Code guide

Frequently asked questions

For mcp-sequentialthinking-tools, edit workspace .vscode/mcp.json. VS Code requires servers rather than mcpServers; preserve the displayed type on each entry.

VS Code's mcp-sequentialthinking-tools example uses stdio.

mcp-sequentialthinking-tools's VS Code configuration invokes npx mcp-sequentialthinking-tools (Node.js/npm).

VS Code's mcp-sequentialthinking-tools example references MAX_HISTORY_SIZE. Check these names if startup or authentication fails; the example alone does not distinguish required from optional values.

mcp-sequentialthinking-tools's stored list contains 3 tools, including sequentialthinking_tools, get_thinking_history, clear_thinking_history. Compare those names with VS Code's connected tool list; the stored list is not a live check.

No. It only validates and stores recommendations authored by the model against an explicitly supplied available-tool list.

Yes. session_id selects a history bucket, with default used when no session is provided.